Overview In this role you drive the development of Physical AI for intelligent surgical robotics, blending model-based robotics with multimodal AI to advance autonomy and workflow intelligence in image-guided procedures. You will collaborate with engineering, clinical, regulatory, and product teams to translate research into robust, production-ready solutions within a regulated medical-device context. You'll stay at the forefront of MedTech AI and contribute to IP creation while shaping system architecture and validation strategies. This is an impact-focused role at Philips' health-tech frontier.
Compensation / Benefits- Total Rewards benefits program
- generous PTO
- 401k with up to 7% match
- HSA with company contributions
- stock purchase plan
- education reimbursement
Responsibilities- Develop Physical AI solutions for surgical robotics by integrating model-based robotics with Vision-Language-Action models
- Design and evaluate AI for image-guided interventions and surgical robotics applications
- Contribute to system architecture, algorithms, experimentation, validation, and regulatory documentation
- Collaborate with system engineering, clinical, regulatory, product management, and marketing teams to translate research into production-ready solutions
- Stay current with MedTech and AI advances and contribute to intellectual property creation
- Lead technical work from concept to implementation within cross-functional and academic partnerships
Key requirements- 5+ years applying AI or robotics to image-guided interventions, surgical robotics, medical imaging, or related domains
- Experience with robotics foundation models, Vision-Language-Action models, multimodal AI, LLMs, or vision models; familiarity with reinforcement learning and learning from demonstrations
- Strong background in model-based motion planning, control, or robotic autonomy
- Proficient in Python and modern AI/ML frameworks; experience training, evaluating, and deploying ML models; knowledge of C++ preferred
- Ability to translate ambitious research into milestone-driven plans, prototypes, validation evidence, and documentation for externally funded programs
- Experience or strong interest in safety-bounded autonomy, uncertainty estimation, fail-safe control, or runtime monitoring for AI-enabled robotics
- Master's or PhD in Robitics, Computer Science, AI or related field; PhD preferred
- Ability to lead technical efforts across cross-functional teams and external partners
- US work authorization and residency near Cambridge, MA
- cross-functional collaboration
- strong communication
- problem-solving orientation
- Vision-Language-Action models (VLA)
- multimodal AI (vision + language + actions)
- large language models (LLMs)
